object-recognition.w09

object-recognition.w09 - The whole is greater than the sum...

Info iconThis preview shows pages 1–37. Sign up to view the full content.

View Full Document Right Arrow Icon
Object recognition
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Synthetic objects are perceived as collections of elementary features put the features together, and, voila! – you get an object!
Background image of page 2
Feature integration theory detect the features (automatic) put the features together (not automatic)
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Illusory conjunction T R
Background image of page 4
But just how do we know what the parts are? Biederman (1981): Recognition by components (sometimes called RBC) Elementary parts called geons an idea he stole from linguistics regions of concavity
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Biederman (1987): Recognition by components (RBC) The components are called “geons” An idea he borrowed from linguistics.
Background image of page 6
What’s The Evidence? Geons Defined By regions Of concavity
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
So far. .. Elementary “parts” are geons. defined by regions of concavity Detection of features is automatic Putting features together is not automatic.
Background image of page 8
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 10
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 12
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 14
Background image of page 15

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 16
Background image of page 17

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 18
Background image of page 19

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 20
Background image of page 21

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 22
Background image of page 23

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 24
Background image of page 25

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 26
Background image of page 27

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 28
Background image of page 29

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 30
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: The whole is greater than the sum of its parts. Gestalt theories of perception Synthetic theories of object recognition Holistic processing Bottom-up versus Top-down processing Holistic vs. featural processing WAIT! (time for a demonstration) Bottom-up versus Top-down processing Connectionist Model Like neural networks? information distributed over lots of units (neurons) inhibition and excitation (just like neurons) EPSP: excitatory post-synaptic potential IPSP: inhibitory post-synaptic potential Desimone, et al are faces special? temporal cortex (Desimone, et al) prosopagnosia inversion effect ---------------------------gone to the dogs What about greebles? (Gauthier & Tarr)...
View Full Document

Page1 / 37

object-recognition.w09 - The whole is greater than the sum...

This preview shows document pages 1 - 37. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online